Qwen Plus 0728 (thinking)

About Qwen Plus 0728 (thinking)

Qwen Plus is Alibaba's balanced cloud-hosted model, offering strong capability at moderate pricing. The model delivers excellent performance on reasoning, coding, and multilingual tasks while being more cost-effective than Qwen Max. Qwen Plus features a substantial context window and supports function calling for building AI applications. It excels at general conversation, content generation, and business automation tasks. The model is optimized for production deployments requiring reliable performance without premium pricing. For organizations seeking capable AI through Alibaba's cloud with favorable economics, Qwen Plus provides excellent value. It's the recommended choice for most production use cases.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Alibaba Qwen Model Lineup

Compare all models from Alibaba Qwen to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

KAT-Coder-Pro V1

Other

Input: $0.21

Output: $0.83

Context: 256k

KAT-Coder-Pro V1

Other

Input: $0.21

Output: $0.83

Context: 256k

DeepSeek V3 0324

DeepSeek

Input: $0.19

Output: $0.87

Context: 164k

Mixtral 8x7B Instruct

Mistral

Input: $0.54

Output: $0.54

Context: 33k

💡 Cheaper Alternatives

Same Brand (Alibaba Qwen)

Cross Brand

🚀 Quick Start

Get started with Qwen Plus 0728 (thinking) API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="qwen/qwen-plus-2025-07-28",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision